Research on small building detection method based on convolutional neural network

Xingchen Wang

doi:10.1117/12.2670482

1 June 2023 Research on small building detection method based on convolutional neural network

Xingchen Wang

Proceedings Volume 12625, International Conference on Mathematics, Modeling, and Computer Science (MMCS2022); 1262528 (2023) https://doi.org/10.1117/12.2670482
Event: International Conference on Mathematics, Modeling and Computer Science (MMCS2022),, 2022, Wuhan, China

Abstract

As one of the main targets of remote sensing technology detection, how to automatically and efficiently extract small buildings from large quantities of data is the main problem of urban planning and construction. At present, although domestic and foreign scholars have made excellent achievements in the research of remote sensing technology, target detection and recognition and extraction cannot fully meet the actual needs because of the inconsistent structure types of small buildings and the complex environment. Therefore, on the basis of understanding the research status of building extraction and convolutional neural network, this paper compares and analyzes the traditional detection algorithm and the semantic segmentation method based on convolutional neural network. The final results show that the extraction results of small buildings are more accurate and meet the needs of current urban planning and construction.

Citation Download Citation

Xingchen Wang "Research on small building detection method based on convolutional neural network", Proc. SPIE 12625, International Conference on Mathematics, Modeling, and Computer Science (MMCS2022), 1262528 (1 June 2023); https://doi.org/10.1117/12.2670482

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available